Synthesis of diagnostic quality cancer pathology images by generative adversarial networks
The DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.
Abstract
Deep learning‐based computer vision methods have recently made remarkable breakthroughs in the analysis and classification of cancer pathology images. However, there has been relatively little investigation of the utility of deep neural networks to synthesize medical images. In this study, we evaluated the efficacy of generative adversarial networks to synthesize high‐resolution pathology images of 10 histological types of cancer, including five cancer types from The Cancer Genome Atlas and the five major histological subtypes of ovarian carcinoma. The quality of these images was assessed using a comprehensive survey of board‐certified pathologists (n = 9) and pathology trainees (n = 6). Our results show that the real and synthetic images are classified by histotype with comparable accuracies and the synthetic images are visually indistinguishable from real images. Furthermore, we trained deep convolutional neural networks to diagnose the different cancer types and determined that the synthetic images perform as well as additional real images when used to supplement a small training set. These findings have important applications in proficiency testing of medical practitioners and quality assurance in clinical laboratories. Furthermore, training of computer‐aided diagnostic systems can benefit from synthetic images where labeled datasets are limited (e.g. rare cancers). We have created a publicly available website where clinicians and researchers can attempt questions from the image survey (http://gan.aimlab.ca/). © 2020 Pathological Society of Great Britain and Ireland. Published by John Wiley & Sons, Ltd.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Interrater reliability: The kappa statistic
McHugh, M. L. (2012) · Biochemia Medica · doi:10.11613/bm.2012.031 · Cited by 19,877
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., et al. (2016) · arXiv · doi:10.48550/arxiv.1603.04467 · Cited by 9,408
Measuring nominal scale agreement among many raters.
Fleiss, J. L. (1971) · Psychological Bulletin · doi:10.1037/h0031619 · Cited by 8,733 · cited 2×
“Analysis of inter-rater agreement demonstrated strong concordance (although lower than the concordance between a rater’s diagnosis and the true diagnosis) for histotype classification, with a Fleiss’ kappa [37] of 0.”
BackgroundMethodImproved Techniques for Training GANs
Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., & Chen, X. (2016) · arXiv · doi:10.48550/arxiv.1606.03498 · Cited by 6,965
Image Style Transfer Using Convolutional Neural Networks
Gatys, L. A., Ecker, A. S., & Bethge, M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.265 · Cited by 6,025
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Karras, T., Aila, T., Laine, S., & Lehtinen, J. (2017) · arXiv · doi:10.48550/arxiv.1710.10196 · Cited by 4,727
Differential Privacy: A Survey of Results
Dwork, C. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-79228-4_1 · Cited by 3,542 · cited 1×
“As the generator network in a GAN has no direct access to the patient images, these models, in combination with differential privacy strategies [49], can capture the features of a dataset and be transferred with minimal risk to patient privacy.”
BackgroundEhteshami Bejnordi, B., Veta, M., Johannes van Diest, P., van Ginneken, B., Karssemeijer, N., Litjens, G., van der Laak, J. A. W. M., and the CAMELYON16 Consortium, Hermsen, M., Manson, Q. F., et al. (2017) · JAMA · doi:10.1001/jama.2017.14585 · Cited by 3,293
Coudray, N., Ocampo, P. S., Sakellaropoulos, T., Narula, N., Snuderl, M., Fenyö, D., Moreira, A. L., Razavian, N., & Tsirigos, A. (2018) · Nature Medicine · doi:10.1038/s41591-018-0177-5 · Cited by 2,930 · cited 1×
“Applications of deep learning to pathology images have shown great potential in a range of tasks, including identifying cancer [1–3], predicting patient outcomes [4–6], and classifying genomic driver mutations [7] and molecular subgroups [8] solely from images.”
BackgroundClinical-grade computational pathology using weakly supervised deep learning on whole slide images
Campanella, G., Hanna, M. G., Geneslaw, L., Miraflor, A., Werneck Krauss Silva, V., Busam, K. J., Brogi, E., Reuter, V. E., Klimstra, D. S., & Fuchs, T. J. (2019) · Nature Medicine · doi:10.1038/s41591-019-0508-1 · Cited by 2,799
Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
Schlegl, T., Seeböck, P., Waldstein, S. M., Schmidt-Erfurth, U., & Langs, G. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-59050-9_12 · Cited by 2,627
The practical implementation of artificial intelligence technologies in medicine
He, J., Baxter, S. L., Xu, J., Xu, J., Zhou, X., & Zhang, K. (2019) · Nature Medicine · doi:10.1038/s41591-018-0307-0 · Cited by 2,246
Toward a Shared Vision for Cancer Genomic Data
Grossman, R. L., Heath, A. P., Ferretti, V., Varmus, H. E., Lowy, D. R., Kibbe, W. A., & Staudt, L. M. (2016) · New England Journal of Medicine · doi:10.1056/nejmp1607591 · Cited by 1,680 · cited 2×
“In order to represent a wide range of distinctive morphologic characteristics, 668 WSIs corresponding to five cancer histotypes were taken from TCGA archive [24] with the following breakdown: LGG (333 slides), HCC (78 slides), LSCC (72 slides), RCC (104 slides), and PTC (81 slides).”
BackgroundPrivacy in the age of medical big data
Price, W. N., & Cohen, I. G. (2019) · Nature Medicine · doi:10.1038/s41591-018-0272-7 · Cited by 1,522
Predicting cancer outcomes from histology and genomics using convolutional networks
Mobadersany, P., Yousefi, S., Amgad, M., Gutman, D. A., Barnholtz-Sloan, J. S., Velázquez Vega, J. E., Brat, D. J., & Cooper, L. A. D. (2018) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1717139115 · Cited by 1,084 · cited 1×
“Applications of deep learning to pathology images have shown great potential in a range of tasks, including identifying cancer, 1–3 predicting patient outcomes, 4–6 and classifying genomic driver mutations 7 and molecular subgroups 8 solely from images.”
BackgroundOvarian Carcinoma Subtypes Are Different Diseases: Implications for Biomarker Studies
Köbel, M., Kalloger, S. E., Boyd, N., McKinney, S., Mehl, E., Palmer, C., Leung, S., Bowen, N. J., Ionescu, D. N., Rajput, A., et al. (2008) · PLoS Medicine · doi:10.1371/journal.pmed.0050232 · Cited by 814 · cited 1×
“36,37 The fact that the synthetic images could be reliably classified supports our assertion that they are of diagnostic quality, which in our view implies that they are usable for directly clinically relevant tasks.”
BackgroundSelf-citationBarratt, S., & Sharma, R. (2018) · arXiv · doi:10.48550/arxiv.1801.01973 · Cited by 732
Deep learning-based classification of mesothelioma improves prediction of patient outcome
Courtiol, P., Maussion, C., Moarii, M., Pronier, E., Pilcer, S., Sefta, M., Manceron, P., Toldo, S., Zaslavskiy, M., Le Stang, N., et al. (2019) · Nature Medicine · doi:10.1038/s41591-019-0583-3 · Cited by 544
Detecting Cancer Metastases on Gigapixel Pathology Images
Liu, Y., Gadepalli, K., Norouzi, M., Dahl, G. E., Kohlberger, T., Boyko, A., Venugopalan, S., Timofeev, A., Nelson, P. Q., Corrado, G. S., et al. (2017) · arXiv · doi:10.48550/arxiv.1703.02442 · Cited by 506 · cited 1×
“We then applied HSV color jitter (during training only) with parameters adopted from [27] (brightness with a maximum delta of 0.”
MethodNagpal, K., Foote, D., Liu, Y., Chen, P.-H. C., Wulczyn, E., Tan, F., Olson, N., Smith, J. L., Mohtashamian, A., Wren, J. H., et al. (2019) · npj Digital Medicine · doi:10.1038/s41746-019-0112-2 · Cited by 495
Steiner, D. F., MacDonald, R., Liu, Y., Truszkowski, P., Hipp, J. D., Gammage, C., Thng, F., Peng, L., & Stumpe, M. C. (2018) · American Journal of Surgical Pathology · doi:10.1097/pas.0000000000001151 · Cited by 489 · cited 1×
“Whereas the initial studies applying deep learning to pathology used datasets of several hundred slides [1,2], more recent work has suggested that upwards of 10 000 slides may be needed to develop and validate a clinical support system that is capable of recognizing the full breadth of variability within pathology ima…”
BackgroundChen, P.-H. C., Gadepalli, K., MacDonald, R., Liu, Y., Kadowaki, S., Nagpal, K., Kohlberger, T., Dean, J., Corrado, G. S., Hipp, J. D., et al. (2019) · Nature Medicine · doi:10.1038/s41591-019-0539-7 · Cited by 342
Cited by
Artificial intelligence in histopathology: enhancing cancer research and clinical oncology
Shmatko, A., Ghaffari Laleh, N., Gerstung, M., & Kather, J. N. (2022) · Nature Cancer · doi:10.1038/s43018-022-00436-4 · Cited by 446
“In computational pathology, GANs can synthesize realistic image patches 110 that retain information about molecular alterations of cancer 111 .”
BackgroundGenerative Artificial Intelligence in Anatomic Pathology
Brodsky, V., Ullah, E., Bychkov, A., Song, A. H., Walk, E. E., Louis, P., Rasool, G., Singh, R. S., Mahmood, F., Bui, M. M., et al. (2025) · Archives of Pathology & Laboratory Medicine · doi:10.5858/arpa.2024-0215-ra · Cited by 48
Rajotte, J.-F., Mukherjee, S., Robinson, C., Ortiz, A., West, C., Ferres, J. M. L., & Ng, R. T. (2021) · Proceedings of the Conference on Information Technology for Social Good · doi:10.1145/3462203.3475875 · Cited by 34
Metadata
- Authors
- Levine, A. B., Peng, J., Farnell, D., Nursey, M., Wang, Y., Naso, J. R., Ren, H., Farahani, H., Chen, C., Chiu, D., Talhouk, A., Sheffield, B., Riazy, M., Ip, P. P., Parra‐Herran, C., Mills, A., Singh, N., Tessier‐Cloutier, B., Salisbury, T., Lee, J., Salcudean, T., Jones, S. J., Huntsman, D. G., Gilks, C. B., Yip, S., & Bashashati, A.
- Venue
- The Journal of Pathology
- Publisher
- Wiley
- Published
- 2020-09-08
- Volume
- 252
- Issue
- 2
- Pages
- 178-188
- ISSN
- 0022-3417 (ISSN-L)
- 1096-9896
- OpenAlex
- W3044753181
- Cited by
- 120
- References
- 22
- FWCI
- 4.74
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.